3 ###############################################################################
5 # This script scrapes the Covid-19 Wikiproject
7 # It (1) hits the fcgi to find out how many rounds. Then (2) hit the fcgi
8 # that many rounds, cooking that information down to just a list of article names and
9 # then (3) saves it out.
12 # the fCGI returns only 1000 max, no matter what you put in the limit. page 1 looks like this....
13 # https://tools.wmflabs.org/enwp10/cgi-bin/list2.fcgi?run=yes&projecta=COVID-19&namespace=&pagename=&quality=&importance=&score=&limit=1000&offset=1&sorta=Importance&sortb=Quality
15 # and page 2 looks like this
16 # https://tools.wmflabs.org/enwp10/cgi-bin/list2.fcgi?namespace=&run=yes&projecta=COVID-19&score=&sorta=Importance&importance=&limit=1000&pagename=&quality=&sortb=Quality&&offset=1001
18 ###############################################################################
27 from bs4 import BeautifulSoup
31 parser = argparse.ArgumentParser(description='Get a list of pages tracked by the COVID-19 Wikiproject.')
32 parser.add_argument('-o', '--output_file', help='Where to save output', default="wikipedia/resources/enwp_wikiproject_covid19_articles.txt", type=str)
33 parser.add_argument('-L', '--logging_level', help='Logging level. Options are debug, info, warning, error, critical. Default: info.', default='info'),
34 parser.add_argument('-W', '--logging_destination', help='Logging destination file. (default: standard error)', type=str),
35 args = parser.parse_args()
42 outputFile = args.output_file
45 loglevel_mapping = { 'debug' : logging.DEBUG,
46 'info' : logging.INFO,
47 'warning' : logging.WARNING,
48 'error' : logging.ERROR,
49 'critical' : logging.CRITICAL }
51 if args.logging_level in loglevel_mapping:
52 loglevel = loglevel_mapping[args.logging_level]
54 print("Choose a valid log level: debug, info, warning, error, or critical")
58 if args.logging_destination:
59 logging.basicConfig(filename=args.logging_destination, filemode='a', level=loglevel)
61 logging.basicConfig(level=loglevel)
63 export_git_hash = subprocess.check_output(['git', 'rev-parse', 'HEAD']).decode().strip()
64 export_git_short_hash = subprocess.check_output(['git', 'rev-parse', '--short', 'HEAD']).decode().strip()
65 export_time = str(datetime.datetime.now())
67 logging.info(f"Starting at {export_time} and destructively outputting article list to {outputFile}.")
68 logging.info(f"Last commit: {export_git_hash}")
70 #1 How many hits to the fcgi?
71 session = requests.Session()
73 originalURL = "https://tools.wmflabs.org/enwp10/cgi-bin/list2.fcgi?run=yes&projecta=COVID-19&namespace=&pagename=&quality=&importance=&score=&limit=1000&offset=1&sorta=Importance&sortb=Quality"
74 headURL = "https://tools.wmflabs.org/enwp10/cgi-bin/list2.fcgi?run=yes&projecta=COVID-19&namespace=&pagename=&quality=&importance=&score=&limit=1000&offset="
75 tailURL = "&sorta=Importance&sortb=Quality" #head + offset + tail = original when offset = 1
77 # find out how many results we have
78 response = session.get(originalURL)
80 soup = BeautifulSoup(response.text, features="html.parser")
81 nodes = soup.find_all('div', class_="navbox")
82 rx = re.compile("Total results:\D*(\d+)")
83 m = rx.search(nodes[0].get_text())
84 #print(nodes[0].get_text())
85 numResults = int(m.group(1))
87 logging.debug(f"fcgi returned {numResults}")
88 rounds = math.ceil(numResults/1000)
90 #2 Fetch and parse down to just the article names
93 for i in range(1, rounds+1):
94 offset = (i - 1)*1000 + 1 #offset is 1, then 1001, then 2001
95 url = f"{headURL}{offset}{tailURL}"
96 response = session.get(url)
97 soup = BeautifulSoup(response.text, features="html.parser") #make fresh soup
98 article_rows = soup.find_all('tr', class_="list-odd") #just the odds first
99 for row in article_rows:
101 articleNames.append(a.get_text())
102 article_rows = soup.find_all('tr', class_="list-even") #now the events
103 for row in article_rows:
105 articleNames.append(a.get_text())
107 #3 Saves the list to a file
109 with open(outputFile, 'w') as f:
110 f.write('\n'.join(articleNames)+'\n')
111 logging.debug(f"Finished scrape and made a new article file at {datetime.datetime.now()}")
114 if __name__ == "__main__":